A machine learning platform to estimate anti-SARS-CoV-2 activities

Strategies for drug discovery and repositioning are urgently need with respect to COVID-19. Here we present REDIAL-2020, a suite of computational models estimating small molecule activities in range SARS-CoV-2-related assays. Models were trained using publicly available, high-throughput screening data by employing different descriptor types various machine learning strategies. describe the development use eleven that span across areas viral entry, replication, live virus infectivity, vitro infectivity human cell toxicity. REDIAL-2020 is available as web application through DrugCentral portal ( http://drugcentral.org/Redial ). The also provides similarity search results display most similar molecules query, well associated experimental data. can serve rapid online tool identifying active COVID-19 treatment. There an urgent identify drugs may be effective against SARS-CoV-2. A platform made predict anti-COVID-19 activity candidate help prioritize compounds virtual screening.